11 files changed, 94 insertions, 26 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 704f58aa79cd..be1e07d4b596 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -76,8 +76,10 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO)     := lzo
 suffix-$(CONFIG_KERNEL_LZ4)     := lz4
 
+RUN_SIZE = $(shell objdump -h vmlinux | \
+             perl $(srctree)/arch/x86/tools/calc_run_size.pl)
 quiet_cmd_mkpiggy = MKPIGGY $@
-      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
+      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
 targets += piggy.S
 $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index cbed1407a5cd..1d7fbbcc196d 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -207,7 +207,8 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
                                 /* push arguments for decompress_kernel: */
-        pushl   $z_output_len   /* decompressed length */
+        pushl   $z_run_size     /* size of kernel with .bss and .brk */
+        pushl   $z_output_len   /* decompressed length, end of relocs */
         leal    z_extract_offset_negative(%ebx), %ebp
         pushl   %ebp            /* output address */
         pushl   $z_input_len    /* input_len */
@@ -217,7 +218,7 @@ relocated:
         pushl   %eax            /* heap area */
         pushl   %esi            /* real mode pointer */
         call    decompress_kernel /* returns kernel location in %eax */
-        addl    $24, %esp
+        addl    $28, %esp
 
 /*
  * Jump to the decompressed kernel.
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 2884e0c3e8a5..6b1766c6c082 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -402,13 +402,16 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
         pushq   %rsi                    /* Save the real mode argument */
+        movq    $z_run_size, %r9        /* size of kernel with .bss and .brk */
+        pushq   %r9
         movq    %rsi, %rdi              /* real mode address */
         leaq    boot_heap(%rip), %rsi   /* malloc area for uncompression */
         leaq    input_data(%rip), %rdx  /* input_data */
         movl    $z_input_len, %ecx      /* input_len */
         movq    %rbp, %r8               /* output target address */
-        movq    $z_output_len, %r9      /* decompressed length */
+        movq    $z_output_len, %r9      /* decompressed length, end of relocs */
         call    decompress_kernel       /* returns kernel location in %rax */
+        popq    %r9
         popq    %rsi
 
 /*
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 57ab74df7eea..30dd59a9f0b4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -358,7 +358,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
                                   unsigned char *input_data,
                                   unsigned long input_len,
                                   unsigned char *output,
-                                  unsigned long output_len)
+                                  unsigned long output_len,
+                                  unsigned long run_size)
 {
         real_mode = rmode;
 
@@ -381,8 +382,14 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
         free_mem_ptr     = heap;        /* Heap */
         free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
-        output = choose_kernel_location(input_data, input_len,
-                                        output, output_len);
+        /*
+         * The memory hole needed for the kernel is the larger of either
+         * the entire decompressed kernel plus relocation table, or the
+         * entire decompressed kernel plus .bss and .brk sections.
+         */
+        output = choose_kernel_location(input_data, input_len, output,
+                                        output_len > run_size ? output_len
+                                                              : run_size);
 
         /* Validate memory location choices. */
         if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index b669ab65bf6c..d8222f213182 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -36,11 +36,13 @@ int main(int argc, char *argv[])
         uint32_t olen;
         long ilen;
         unsigned long offs;
+        unsigned long run_size;
         FILE *f = NULL;
         int retval = 1;
 
-        if (argc < 2) {
-                fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+        if (argc < 3) {
+                fprintf(stderr, "Usage: %s compressed_file run_size\n",
+                                argv[0]);
                 goto bail;
         }
 
@@ -74,6 +76,7 @@ int main(int argc, char *argv[])
         offs += olen >> 12;     /* Add 8 bytes for each 32K block */
         offs += 64*1024 + 128;  /* Add 64K + 128 bytes slack */
         offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+        run_size = atoi(argv[2]);
 
         printf(".section \".rodata..compressed\",\"a\",@progbits\n");
         printf(".globl z_input_len\n");
@@ -85,6 +88,8 @@ int main(int argc, char *argv[])
         /* z_extract_offset_negative allows simplification of head_32.S */
         printf(".globl z_extract_offset_negative\n");
         printf("z_extract_offset_negative = -0x%lx\n", offs);
+        printf(".globl z_run_size\n");
+        printf("z_run_size = %lu\n", run_size);
 
         printf(".globl input_data, input_data_end\n");
         printf("input_data:\n");
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 8cd27e08e23c..8cd1cc3bc835 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -150,6 +150,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 }
 
 void cpu_disable_common(void);
+void cpu_die_common(unsigned int cpu);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 7aa1acc79789..06674473b0e6 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size)
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
  */
-static void apply_ucode_in_initrd(void *ucode, size_t size)
+static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
 {
         struct equiv_cpu_entry *eq;
         size_t *cont_sz;
         u32 *header;
         u8  *data, **cont;
+        u8 (*patch)[PATCH_MAX_SIZE];
         u16 eq_id = 0;
         int offset, left;
         u32 rev, eax, ebx, ecx, edx;
@@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
         new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
         cont_sz = (size_t *)__pa_nodebug(&container_size);
         cont    = (u8 **)__pa_nodebug(&container);
+        patch   = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
 #else
         new_rev = &ucode_new_rev;
         cont_sz = &container_size;
         cont    = &container;
+        patch   = &amd_ucode_patch;
 #endif
 
         data   = ucode;
@@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
                                 rev = mc->hdr.patch_id;
                                 *new_rev = rev;
 
-                                /* save ucode patch */
-                                memcpy(amd_ucode_patch, mc,
-                                       min_t(u32, header[1], PATCH_MAX_SIZE));
+                                if (save_patch)
+                                        memcpy(patch, mc,
+                                               min_t(u32, header[1], PATCH_MAX_SIZE));
                         }
                 }
 
@@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void)
         *data = cp.data;
         *size = cp.size;
 
-        apply_ucode_in_initrd(cp.data, cp.size);
+        apply_ucode_in_initrd(cp.data, cp.size, true);
 }
 
 #ifdef CONFIG_X86_32
@@ -263,7 +266,7 @@ void load_ucode_amd_ap(void)
         size_t *usize;
         void **ucode;
 
-        mc = (struct microcode_amd *)__pa(amd_ucode_patch);
+        mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
         if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
                 __apply_microcode_amd(mc);
                 return;
@@ -275,7 +278,7 @@ void load_ucode_amd_ap(void)
         if (!*ucode || !*usize)
                 return;
 
-        apply_ucode_in_initrd(*ucode, *usize);
+        apply_ucode_in_initrd(*ucode, *usize, false);
 }
 
 static void __init collect_cpu_sig_on_bsp(void *arg)
@@ -339,7 +342,7 @@ void load_ucode_amd_ap(void)
                  * AP has a different equivalence ID than BSP, looks like
                  * mixed-steppings silicon so go through the ucode blob anew.
                  */
-                apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
+                apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false);
         }
 }
 #endif
@@ -347,7 +350,9 @@ void load_ucode_amd_ap(void)
 int __init save_microcode_in_initrd_amd(void)
 {
         unsigned long cont;
+        int retval = 0;
         enum ucode_state ret;
+        u8 *cont_va;
         u32 eax;
 
         if (!container)
@@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void)
 
 #ifdef CONFIG_X86_32
         get_bsp_sig();
-        cont = (unsigned long)container;
+        cont    = (unsigned long)container;
+        cont_va = __va(container);
 #else
         /*
          * We need the physical address of the container for both bitness since
          * boot_params.hdr.ramdisk_image is a physical address.
          */
-        cont = __pa(container);
+        cont    = __pa(container);
+        cont_va = container;
 #endif
 
         /*
@@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void)
         if (relocated_ramdisk)
                 container = (u8 *)(__va(relocated_ramdisk) +
                              (cont - boot_params.hdr.ramdisk_image));
+        else
+                container = cont_va;
 
         if (ucode_new_rev)
                 pr_info("microcode: updated early to new patch_level=0x%08x\n",
@@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void)
 
         ret = load_microcode_amd(eax, container, container_size);
         if (ret != UCODE_OK)
-                return -EINVAL;
+                retval = -EINVAL;
 
         /*
          * This will be freed any msec now, stash patches for the current
@@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void)
         container = NULL;
         container_size = 0;
 
-        return 0;
+        return retval;
 }
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index 5f28a64e71ea..2c017f242a78 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -124,7 +124,7 @@ void __init load_ucode_bsp(void)
 static bool check_loader_disabled_ap(void)
 {
 #ifdef CONFIG_X86_32
-        return __pa_nodebug(dis_ucode_ldr);
+        return *((bool *)__pa_nodebug(&dis_ucode_ldr));
 #else
         return dis_ucode_ldr;
 #endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4d2128ac70bd..668d8f2a8781 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1303,10 +1303,14 @@ static void __ref remove_cpu_from_maps(int cpu)
         numa_remove_cpu(cpu);
 }
 
+static DEFINE_PER_CPU(struct completion, die_complete);
+
 void cpu_disable_common(void)
 {
         int cpu = smp_processor_id();
 
+        init_completion(&per_cpu(die_complete, smp_processor_id()));
+
         remove_siblinginfo(cpu);
 
         /* It's now safe to remove this processor from the online map */
@@ -1316,8 +1320,6 @@ void cpu_disable_common(void)
         fixup_irqs();
 }
 
-static DEFINE_PER_CPU(struct completion, die_complete);
-
 int native_cpu_disable(void)
 {
         int ret;
@@ -1327,16 +1329,21 @@ int native_cpu_disable(void)
                 return ret;
 
         clear_local_APIC();
-        init_completion(&per_cpu(die_complete, smp_processor_id()));
         cpu_disable_common();
 
         return 0;
 }
 
+void cpu_die_common(unsigned int cpu)
+{
+        wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+}
+
 void native_cpu_die(unsigned int cpu)
 {
         /* We don't do anything here: idle task is faking death itself. */
-        wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+
+        cpu_die_common(cpu);
 
         /* They ack this in play_dead() by setting CPU_DEAD */
         if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
new file mode 100644
index 000000000000..0b0b124d3ece
--- /dev/null
+++ b/arch/x86/tools/calc_run_size.pl
@@ -0,0 +1,30 @@
+#!/usr/bin/perl
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | perl calc_run_size.pl
+use strict;
+
+my $mem_size = 0;
+my $file_offset = 0;
+
+my $sections=" *[0-9]+ \.(?:bss|brk) +";
+while (<>) {
+        if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
+                my $size = hex($1);
+                my $offset = hex($2);
+                $mem_size += $size;
+                if ($file_offset == 0) {
+                        $file_offset = $offset;
+                } elsif ($file_offset != $offset) {
+                        die ".bss and .brk lack common file offset\n";
+                }
+        }
+}
+
+if ($file_offset == 0) {
+        die "Never found .bss or .brk file offset\n";
+}
+printf("%d\n", $mem_size + $file_offset);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8650cdb53209..4c071aeb8417 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -510,6 +510,9 @@ static void xen_cpu_die(unsigned int cpu)
                 current->state = TASK_UNINTERRUPTIBLE;
                 schedule_timeout(HZ/10);
         }
+
+        cpu_die_common(cpu);
+
         xen_smp_intr_free(cpu);
         xen_uninit_lock_cpu(cpu);
         xen_teardown_timer(cpu);